Wolfies at SemEval-2022 Task 8: Feature extraction pipeline with transformers for Multi-lingual news article similarity
This work addresses the challenge of multilingual news article similarity for natural language processing applications, but it is incremental as it builds on existing transformer models and methods.
The authors tackled the problem of measuring similarity between multilingual news articles using seven different metrics, achieving significant improvement over baseline results by employing feature extraction pipelines and a feed-forward neural network.
This work is about finding the similarity between a pair of news articles. There are seven different objective similarity metrics provided in the dataset for each pair and the news articles are in multiple different languages. On top of the pre-trained embedding model, we calculated cosine similarity for baseline results and feed-forward neural network was then trained on top of it to improve the results. We also built separate pipelines for each similarity metric for feature extraction. We could see significant improvement from baseline results using feature extraction and feed-forward neural network.